© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14462
    Prev
    Next
    INDEX
    Explanations

    conditional statements and assertions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with conditional statements/assertions

    np_acts-logits-general · gemini-2.0-flash

    if statements follow parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')")
    -0.58
    <![
    -0.55
     prisma
    -0.54
    )')
    -0.53
     CreateTagHelper
    -0.53
     PhpStorm
    -0.52
    msgTypes
    -0.52
     AttributeSet
    -0.52
     jadx
    -0.51
     كومونز
    -0.50
    POSITIVE LOGITS
    (_
    2.48
     _
    2.30
    =_
    2.25
     (_
    2.23
    [_
    2.03
    :_
    2.01
     {_
    1.99
     [_
    1.95
    {_
    1.91
    ,_
    1.89
    Activations Density 0.185%

    No Known Activations